pyxllib 0.3.96__py3-none-any.whl → 0.3.200__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (358) hide show
  1. pyxllib/__init__.py +21 -21
  2. pyxllib/algo/__init__.py +8 -8
  3. pyxllib/algo/disjoint.py +54 -54
  4. pyxllib/algo/geo.py +541 -529
  5. pyxllib/algo/intervals.py +964 -964
  6. pyxllib/algo/matcher.py +389 -311
  7. pyxllib/algo/newbie.py +166 -166
  8. pyxllib/algo/pupil.py +629 -461
  9. pyxllib/algo/shapelylib.py +67 -67
  10. pyxllib/algo/specialist.py +241 -240
  11. pyxllib/algo/stat.py +494 -458
  12. pyxllib/algo/treelib.py +149 -149
  13. pyxllib/algo/unitlib.py +66 -66
  14. {pyxlpr → pyxllib/autogui}/__init__.py +5 -5
  15. pyxllib/autogui/activewin.py +246 -0
  16. pyxllib/autogui/all.py +9 -0
  17. pyxllib/{ext/autogui → autogui}/autogui.py +852 -823
  18. pyxllib/autogui/uiautolib.py +362 -0
  19. pyxllib/{ext/autogui → autogui}/virtualkey.py +102 -102
  20. pyxllib/autogui/wechat.py +827 -0
  21. pyxllib/autogui/wechat_msg.py +421 -0
  22. pyxllib/autogui/wxautolib.py +84 -0
  23. pyxllib/cv/__init__.py +5 -5
  24. pyxllib/cv/expert.py +267 -267
  25. pyxllib/cv/imfile.py +159 -159
  26. pyxllib/cv/imhash.py +39 -39
  27. pyxllib/cv/pupil.py +9 -9
  28. pyxllib/cv/rgbfmt.py +1525 -1525
  29. pyxllib/cv/slidercaptcha.py +137 -0
  30. pyxllib/cv/trackbartools.py +251 -251
  31. pyxllib/cv/xlcvlib.py +1040 -1040
  32. pyxllib/cv/xlpillib.py +423 -423
  33. pyxllib/data/echarts.py +240 -129
  34. pyxllib/data/jsonlib.py +89 -0
  35. pyxllib/data/oss.py +72 -72
  36. pyxllib/data/pglib.py +1127 -643
  37. pyxllib/data/sqlite.py +568 -341
  38. pyxllib/data/sqllib.py +297 -297
  39. pyxllib/ext/JLineViewer.py +505 -492
  40. pyxllib/ext/__init__.py +6 -6
  41. pyxllib/ext/demolib.py +246 -246
  42. pyxllib/ext/drissionlib.py +277 -0
  43. pyxllib/ext/kq5034lib.py +12 -1606
  44. pyxllib/ext/old.py +663 -663
  45. pyxllib/ext/qt.py +449 -449
  46. pyxllib/ext/robustprocfile.py +497 -0
  47. pyxllib/ext/seleniumlib.py +76 -76
  48. pyxllib/ext/tk.py +173 -173
  49. pyxllib/ext/unixlib.py +827 -826
  50. pyxllib/ext/utools.py +351 -338
  51. pyxllib/ext/webhook.py +124 -101
  52. pyxllib/ext/win32lib.py +40 -40
  53. pyxllib/ext/wjxlib.py +88 -0
  54. pyxllib/ext/wpsapi.py +124 -0
  55. pyxllib/ext/xlwork.py +9 -0
  56. pyxllib/ext/yuquelib.py +1105 -173
  57. pyxllib/file/__init__.py +17 -17
  58. pyxllib/file/docxlib.py +761 -761
  59. pyxllib/file/gitlib.py +309 -309
  60. pyxllib/file/libreoffice.py +165 -0
  61. pyxllib/file/movielib.py +148 -139
  62. pyxllib/file/newbie.py +10 -10
  63. pyxllib/file/onenotelib.py +1469 -1469
  64. pyxllib/file/packlib/__init__.py +330 -293
  65. pyxllib/file/packlib/zipfile.py +2441 -2441
  66. pyxllib/file/pdflib.py +426 -426
  67. pyxllib/file/pupil.py +185 -185
  68. pyxllib/file/specialist/__init__.py +685 -685
  69. pyxllib/file/specialist/dirlib.py +799 -799
  70. pyxllib/file/specialist/download.py +193 -186
  71. pyxllib/file/specialist/filelib.py +2829 -2618
  72. pyxllib/file/xlsxlib.py +3131 -2976
  73. pyxllib/file/xlsyncfile.py +341 -0
  74. pyxllib/prog/__init__.py +5 -5
  75. pyxllib/prog/cachetools.py +64 -0
  76. pyxllib/prog/deprecatedlib.py +233 -233
  77. pyxllib/prog/filelock.py +42 -0
  78. pyxllib/prog/ipyexec.py +253 -253
  79. pyxllib/prog/multiprogs.py +940 -0
  80. pyxllib/prog/newbie.py +451 -444
  81. pyxllib/prog/pupil.py +1197 -1128
  82. pyxllib/prog/sitepackages.py +33 -33
  83. pyxllib/prog/specialist/__init__.py +391 -217
  84. pyxllib/prog/specialist/bc.py +203 -200
  85. pyxllib/prog/specialist/browser.py +497 -488
  86. pyxllib/prog/specialist/common.py +347 -347
  87. pyxllib/prog/specialist/datetime.py +199 -131
  88. pyxllib/prog/specialist/tictoc.py +240 -241
  89. pyxllib/prog/specialist/xllog.py +180 -180
  90. pyxllib/prog/xlosenv.py +108 -101
  91. pyxllib/stdlib/__init__.py +17 -17
  92. pyxllib/stdlib/tablepyxl/__init__.py +10 -10
  93. pyxllib/stdlib/tablepyxl/style.py +303 -303
  94. pyxllib/stdlib/tablepyxl/tablepyxl.py +130 -130
  95. pyxllib/text/__init__.py +8 -8
  96. pyxllib/text/ahocorasick.py +39 -39
  97. pyxllib/text/airscript.js +744 -0
  98. pyxllib/text/charclasslib.py +121 -109
  99. pyxllib/text/jiebalib.py +267 -264
  100. pyxllib/text/jinjalib.py +32 -0
  101. pyxllib/text/jsa_ai_prompt.md +271 -0
  102. pyxllib/text/jscode.py +922 -767
  103. pyxllib/text/latex/__init__.py +158 -158
  104. pyxllib/text/levenshtein.py +303 -303
  105. pyxllib/text/nestenv.py +1215 -1215
  106. pyxllib/text/newbie.py +300 -288
  107. pyxllib/text/pupil/__init__.py +8 -8
  108. pyxllib/text/pupil/common.py +1121 -1095
  109. pyxllib/text/pupil/xlalign.py +326 -326
  110. pyxllib/text/pycode.py +47 -47
  111. pyxllib/text/specialist/__init__.py +8 -8
  112. pyxllib/text/specialist/common.py +112 -112
  113. pyxllib/text/specialist/ptag.py +186 -186
  114. pyxllib/text/spellchecker.py +172 -172
  115. pyxllib/text/templates/echart_base.html +11 -0
  116. pyxllib/text/templates/highlight_code.html +17 -0
  117. pyxllib/text/templates/latex_editor.html +103 -0
  118. pyxllib/text/vbacode.py +17 -17
  119. pyxllib/text/xmllib.py +747 -685
  120. pyxllib/xl.py +42 -38
  121. pyxllib/xlcv.py +17 -17
  122. pyxllib-0.3.200.dist-info/METADATA +48 -0
  123. pyxllib-0.3.200.dist-info/RECORD +126 -0
  124. {pyxllib-0.3.96.dist-info → pyxllib-0.3.200.dist-info}/WHEEL +1 -2
  125. {pyxllib-0.3.96.dist-info → pyxllib-0.3.200.dist-info/licenses}/LICENSE +190 -190
  126. pyxllib/ext/autogui/__init__.py +0 -8
  127. pyxllib-0.3.96.dist-info/METADATA +0 -51
  128. pyxllib-0.3.96.dist-info/RECORD +0 -333
  129. pyxllib-0.3.96.dist-info/top_level.txt +0 -2
  130. pyxlpr/ai/__init__.py +0 -5
  131. pyxlpr/ai/clientlib.py +0 -1281
  132. pyxlpr/ai/specialist.py +0 -286
  133. pyxlpr/ai/torch_app.py +0 -172
  134. pyxlpr/ai/xlpaddle.py +0 -655
  135. pyxlpr/ai/xltorch.py +0 -705
  136. pyxlpr/data/__init__.py +0 -11
  137. pyxlpr/data/coco.py +0 -1325
  138. pyxlpr/data/datacls.py +0 -365
  139. pyxlpr/data/datasets.py +0 -200
  140. pyxlpr/data/gptlib.py +0 -1291
  141. pyxlpr/data/icdar/__init__.py +0 -96
  142. pyxlpr/data/icdar/deteval.py +0 -377
  143. pyxlpr/data/icdar/icdar2013.py +0 -341
  144. pyxlpr/data/icdar/iou.py +0 -340
  145. pyxlpr/data/icdar/rrc_evaluation_funcs_1_1.py +0 -463
  146. pyxlpr/data/imtextline.py +0 -473
  147. pyxlpr/data/labelme.py +0 -866
  148. pyxlpr/data/removeline.py +0 -179
  149. pyxlpr/data/specialist.py +0 -57
  150. pyxlpr/eval/__init__.py +0 -85
  151. pyxlpr/paddleocr.py +0 -776
  152. pyxlpr/ppocr/__init__.py +0 -15
  153. pyxlpr/ppocr/configs/rec/multi_language/generate_multi_language_configs.py +0 -226
  154. pyxlpr/ppocr/data/__init__.py +0 -135
  155. pyxlpr/ppocr/data/imaug/ColorJitter.py +0 -26
  156. pyxlpr/ppocr/data/imaug/__init__.py +0 -67
  157. pyxlpr/ppocr/data/imaug/copy_paste.py +0 -170
  158. pyxlpr/ppocr/data/imaug/east_process.py +0 -437
  159. pyxlpr/ppocr/data/imaug/gen_table_mask.py +0 -244
  160. pyxlpr/ppocr/data/imaug/iaa_augment.py +0 -114
  161. pyxlpr/ppocr/data/imaug/label_ops.py +0 -789
  162. pyxlpr/ppocr/data/imaug/make_border_map.py +0 -184
  163. pyxlpr/ppocr/data/imaug/make_pse_gt.py +0 -106
  164. pyxlpr/ppocr/data/imaug/make_shrink_map.py +0 -126
  165. pyxlpr/ppocr/data/imaug/operators.py +0 -433
  166. pyxlpr/ppocr/data/imaug/pg_process.py +0 -906
  167. pyxlpr/ppocr/data/imaug/randaugment.py +0 -143
  168. pyxlpr/ppocr/data/imaug/random_crop_data.py +0 -239
  169. pyxlpr/ppocr/data/imaug/rec_img_aug.py +0 -533
  170. pyxlpr/ppocr/data/imaug/sast_process.py +0 -777
  171. pyxlpr/ppocr/data/imaug/text_image_aug/__init__.py +0 -17
  172. pyxlpr/ppocr/data/imaug/text_image_aug/augment.py +0 -120
  173. pyxlpr/ppocr/data/imaug/text_image_aug/warp_mls.py +0 -168
  174. pyxlpr/ppocr/data/lmdb_dataset.py +0 -115
  175. pyxlpr/ppocr/data/pgnet_dataset.py +0 -104
  176. pyxlpr/ppocr/data/pubtab_dataset.py +0 -107
  177. pyxlpr/ppocr/data/simple_dataset.py +0 -372
  178. pyxlpr/ppocr/losses/__init__.py +0 -61
  179. pyxlpr/ppocr/losses/ace_loss.py +0 -52
  180. pyxlpr/ppocr/losses/basic_loss.py +0 -135
  181. pyxlpr/ppocr/losses/center_loss.py +0 -88
  182. pyxlpr/ppocr/losses/cls_loss.py +0 -30
  183. pyxlpr/ppocr/losses/combined_loss.py +0 -67
  184. pyxlpr/ppocr/losses/det_basic_loss.py +0 -208
  185. pyxlpr/ppocr/losses/det_db_loss.py +0 -80
  186. pyxlpr/ppocr/losses/det_east_loss.py +0 -63
  187. pyxlpr/ppocr/losses/det_pse_loss.py +0 -149
  188. pyxlpr/ppocr/losses/det_sast_loss.py +0 -121
  189. pyxlpr/ppocr/losses/distillation_loss.py +0 -272
  190. pyxlpr/ppocr/losses/e2e_pg_loss.py +0 -140
  191. pyxlpr/ppocr/losses/kie_sdmgr_loss.py +0 -113
  192. pyxlpr/ppocr/losses/rec_aster_loss.py +0 -99
  193. pyxlpr/ppocr/losses/rec_att_loss.py +0 -39
  194. pyxlpr/ppocr/losses/rec_ctc_loss.py +0 -44
  195. pyxlpr/ppocr/losses/rec_enhanced_ctc_loss.py +0 -70
  196. pyxlpr/ppocr/losses/rec_nrtr_loss.py +0 -30
  197. pyxlpr/ppocr/losses/rec_sar_loss.py +0 -28
  198. pyxlpr/ppocr/losses/rec_srn_loss.py +0 -47
  199. pyxlpr/ppocr/losses/table_att_loss.py +0 -109
  200. pyxlpr/ppocr/metrics/__init__.py +0 -44
  201. pyxlpr/ppocr/metrics/cls_metric.py +0 -45
  202. pyxlpr/ppocr/metrics/det_metric.py +0 -82
  203. pyxlpr/ppocr/metrics/distillation_metric.py +0 -73
  204. pyxlpr/ppocr/metrics/e2e_metric.py +0 -86
  205. pyxlpr/ppocr/metrics/eval_det_iou.py +0 -274
  206. pyxlpr/ppocr/metrics/kie_metric.py +0 -70
  207. pyxlpr/ppocr/metrics/rec_metric.py +0 -75
  208. pyxlpr/ppocr/metrics/table_metric.py +0 -50
  209. pyxlpr/ppocr/modeling/architectures/__init__.py +0 -32
  210. pyxlpr/ppocr/modeling/architectures/base_model.py +0 -88
  211. pyxlpr/ppocr/modeling/architectures/distillation_model.py +0 -60
  212. pyxlpr/ppocr/modeling/backbones/__init__.py +0 -54
  213. pyxlpr/ppocr/modeling/backbones/det_mobilenet_v3.py +0 -268
  214. pyxlpr/ppocr/modeling/backbones/det_resnet_vd.py +0 -246
  215. pyxlpr/ppocr/modeling/backbones/det_resnet_vd_sast.py +0 -285
  216. pyxlpr/ppocr/modeling/backbones/e2e_resnet_vd_pg.py +0 -265
  217. pyxlpr/ppocr/modeling/backbones/kie_unet_sdmgr.py +0 -186
  218. pyxlpr/ppocr/modeling/backbones/rec_mobilenet_v3.py +0 -138
  219. pyxlpr/ppocr/modeling/backbones/rec_mv1_enhance.py +0 -258
  220. pyxlpr/ppocr/modeling/backbones/rec_nrtr_mtb.py +0 -48
  221. pyxlpr/ppocr/modeling/backbones/rec_resnet_31.py +0 -210
  222. pyxlpr/ppocr/modeling/backbones/rec_resnet_aster.py +0 -143
  223. pyxlpr/ppocr/modeling/backbones/rec_resnet_fpn.py +0 -307
  224. pyxlpr/ppocr/modeling/backbones/rec_resnet_vd.py +0 -286
  225. pyxlpr/ppocr/modeling/heads/__init__.py +0 -54
  226. pyxlpr/ppocr/modeling/heads/cls_head.py +0 -52
  227. pyxlpr/ppocr/modeling/heads/det_db_head.py +0 -118
  228. pyxlpr/ppocr/modeling/heads/det_east_head.py +0 -121
  229. pyxlpr/ppocr/modeling/heads/det_pse_head.py +0 -37
  230. pyxlpr/ppocr/modeling/heads/det_sast_head.py +0 -128
  231. pyxlpr/ppocr/modeling/heads/e2e_pg_head.py +0 -253
  232. pyxlpr/ppocr/modeling/heads/kie_sdmgr_head.py +0 -206
  233. pyxlpr/ppocr/modeling/heads/multiheadAttention.py +0 -163
  234. pyxlpr/ppocr/modeling/heads/rec_aster_head.py +0 -393
  235. pyxlpr/ppocr/modeling/heads/rec_att_head.py +0 -202
  236. pyxlpr/ppocr/modeling/heads/rec_ctc_head.py +0 -88
  237. pyxlpr/ppocr/modeling/heads/rec_nrtr_head.py +0 -826
  238. pyxlpr/ppocr/modeling/heads/rec_sar_head.py +0 -402
  239. pyxlpr/ppocr/modeling/heads/rec_srn_head.py +0 -280
  240. pyxlpr/ppocr/modeling/heads/self_attention.py +0 -406
  241. pyxlpr/ppocr/modeling/heads/table_att_head.py +0 -246
  242. pyxlpr/ppocr/modeling/necks/__init__.py +0 -32
  243. pyxlpr/ppocr/modeling/necks/db_fpn.py +0 -111
  244. pyxlpr/ppocr/modeling/necks/east_fpn.py +0 -188
  245. pyxlpr/ppocr/modeling/necks/fpn.py +0 -138
  246. pyxlpr/ppocr/modeling/necks/pg_fpn.py +0 -314
  247. pyxlpr/ppocr/modeling/necks/rnn.py +0 -92
  248. pyxlpr/ppocr/modeling/necks/sast_fpn.py +0 -284
  249. pyxlpr/ppocr/modeling/necks/table_fpn.py +0 -110
  250. pyxlpr/ppocr/modeling/transforms/__init__.py +0 -28
  251. pyxlpr/ppocr/modeling/transforms/stn.py +0 -135
  252. pyxlpr/ppocr/modeling/transforms/tps.py +0 -308
  253. pyxlpr/ppocr/modeling/transforms/tps_spatial_transformer.py +0 -156
  254. pyxlpr/ppocr/optimizer/__init__.py +0 -61
  255. pyxlpr/ppocr/optimizer/learning_rate.py +0 -228
  256. pyxlpr/ppocr/optimizer/lr_scheduler.py +0 -49
  257. pyxlpr/ppocr/optimizer/optimizer.py +0 -160
  258. pyxlpr/ppocr/optimizer/regularizer.py +0 -52
  259. pyxlpr/ppocr/postprocess/__init__.py +0 -55
  260. pyxlpr/ppocr/postprocess/cls_postprocess.py +0 -33
  261. pyxlpr/ppocr/postprocess/db_postprocess.py +0 -234
  262. pyxlpr/ppocr/postprocess/east_postprocess.py +0 -143
  263. pyxlpr/ppocr/postprocess/locality_aware_nms.py +0 -200
  264. pyxlpr/ppocr/postprocess/pg_postprocess.py +0 -52
  265. pyxlpr/ppocr/postprocess/pse_postprocess/__init__.py +0 -15
  266. pyxlpr/ppocr/postprocess/pse_postprocess/pse/__init__.py +0 -29
  267. pyxlpr/ppocr/postprocess/pse_postprocess/pse/setup.py +0 -14
  268. pyxlpr/ppocr/postprocess/pse_postprocess/pse_postprocess.py +0 -118
  269. pyxlpr/ppocr/postprocess/rec_postprocess.py +0 -654
  270. pyxlpr/ppocr/postprocess/sast_postprocess.py +0 -355
  271. pyxlpr/ppocr/tools/__init__.py +0 -14
  272. pyxlpr/ppocr/tools/eval.py +0 -83
  273. pyxlpr/ppocr/tools/export_center.py +0 -77
  274. pyxlpr/ppocr/tools/export_model.py +0 -129
  275. pyxlpr/ppocr/tools/infer/predict_cls.py +0 -151
  276. pyxlpr/ppocr/tools/infer/predict_det.py +0 -300
  277. pyxlpr/ppocr/tools/infer/predict_e2e.py +0 -169
  278. pyxlpr/ppocr/tools/infer/predict_rec.py +0 -414
  279. pyxlpr/ppocr/tools/infer/predict_system.py +0 -204
  280. pyxlpr/ppocr/tools/infer/utility.py +0 -629
  281. pyxlpr/ppocr/tools/infer_cls.py +0 -83
  282. pyxlpr/ppocr/tools/infer_det.py +0 -134
  283. pyxlpr/ppocr/tools/infer_e2e.py +0 -122
  284. pyxlpr/ppocr/tools/infer_kie.py +0 -153
  285. pyxlpr/ppocr/tools/infer_rec.py +0 -146
  286. pyxlpr/ppocr/tools/infer_table.py +0 -107
  287. pyxlpr/ppocr/tools/program.py +0 -596
  288. pyxlpr/ppocr/tools/test_hubserving.py +0 -117
  289. pyxlpr/ppocr/tools/train.py +0 -163
  290. pyxlpr/ppocr/tools/xlprog.py +0 -748
  291. pyxlpr/ppocr/utils/EN_symbol_dict.txt +0 -94
  292. pyxlpr/ppocr/utils/__init__.py +0 -24
  293. pyxlpr/ppocr/utils/dict/ar_dict.txt +0 -117
  294. pyxlpr/ppocr/utils/dict/arabic_dict.txt +0 -162
  295. pyxlpr/ppocr/utils/dict/be_dict.txt +0 -145
  296. pyxlpr/ppocr/utils/dict/bg_dict.txt +0 -140
  297. pyxlpr/ppocr/utils/dict/chinese_cht_dict.txt +0 -8421
  298. pyxlpr/ppocr/utils/dict/cyrillic_dict.txt +0 -163
  299. pyxlpr/ppocr/utils/dict/devanagari_dict.txt +0 -167
  300. pyxlpr/ppocr/utils/dict/en_dict.txt +0 -63
  301. pyxlpr/ppocr/utils/dict/fa_dict.txt +0 -136
  302. pyxlpr/ppocr/utils/dict/french_dict.txt +0 -136
  303. pyxlpr/ppocr/utils/dict/german_dict.txt +0 -143
  304. pyxlpr/ppocr/utils/dict/hi_dict.txt +0 -162
  305. pyxlpr/ppocr/utils/dict/it_dict.txt +0 -118
  306. pyxlpr/ppocr/utils/dict/japan_dict.txt +0 -4399
  307. pyxlpr/ppocr/utils/dict/ka_dict.txt +0 -153
  308. pyxlpr/ppocr/utils/dict/korean_dict.txt +0 -3688
  309. pyxlpr/ppocr/utils/dict/latin_dict.txt +0 -185
  310. pyxlpr/ppocr/utils/dict/mr_dict.txt +0 -153
  311. pyxlpr/ppocr/utils/dict/ne_dict.txt +0 -153
  312. pyxlpr/ppocr/utils/dict/oc_dict.txt +0 -96
  313. pyxlpr/ppocr/utils/dict/pu_dict.txt +0 -130
  314. pyxlpr/ppocr/utils/dict/rs_dict.txt +0 -91
  315. pyxlpr/ppocr/utils/dict/rsc_dict.txt +0 -134
  316. pyxlpr/ppocr/utils/dict/ru_dict.txt +0 -125
  317. pyxlpr/ppocr/utils/dict/ta_dict.txt +0 -128
  318. pyxlpr/ppocr/utils/dict/table_dict.txt +0 -277
  319. pyxlpr/ppocr/utils/dict/table_structure_dict.txt +0 -2759
  320. pyxlpr/ppocr/utils/dict/te_dict.txt +0 -151
  321. pyxlpr/ppocr/utils/dict/ug_dict.txt +0 -114
  322. pyxlpr/ppocr/utils/dict/uk_dict.txt +0 -142
  323. pyxlpr/ppocr/utils/dict/ur_dict.txt +0 -137
  324. pyxlpr/ppocr/utils/dict/xi_dict.txt +0 -110
  325. pyxlpr/ppocr/utils/dict90.txt +0 -90
  326. pyxlpr/ppocr/utils/e2e_metric/Deteval.py +0 -574
  327. pyxlpr/ppocr/utils/e2e_metric/polygon_fast.py +0 -83
  328. pyxlpr/ppocr/utils/e2e_utils/extract_batchsize.py +0 -87
  329. pyxlpr/ppocr/utils/e2e_utils/extract_textpoint_fast.py +0 -457
  330. pyxlpr/ppocr/utils/e2e_utils/extract_textpoint_slow.py +0 -592
  331. pyxlpr/ppocr/utils/e2e_utils/pgnet_pp_utils.py +0 -162
  332. pyxlpr/ppocr/utils/e2e_utils/visual.py +0 -162
  333. pyxlpr/ppocr/utils/en_dict.txt +0 -95
  334. pyxlpr/ppocr/utils/gen_label.py +0 -81
  335. pyxlpr/ppocr/utils/ic15_dict.txt +0 -36
  336. pyxlpr/ppocr/utils/iou.py +0 -54
  337. pyxlpr/ppocr/utils/logging.py +0 -69
  338. pyxlpr/ppocr/utils/network.py +0 -84
  339. pyxlpr/ppocr/utils/ppocr_keys_v1.txt +0 -6623
  340. pyxlpr/ppocr/utils/profiler.py +0 -110
  341. pyxlpr/ppocr/utils/save_load.py +0 -150
  342. pyxlpr/ppocr/utils/stats.py +0 -72
  343. pyxlpr/ppocr/utils/utility.py +0 -80
  344. pyxlpr/ppstructure/__init__.py +0 -13
  345. pyxlpr/ppstructure/predict_system.py +0 -187
  346. pyxlpr/ppstructure/table/__init__.py +0 -13
  347. pyxlpr/ppstructure/table/eval_table.py +0 -72
  348. pyxlpr/ppstructure/table/matcher.py +0 -192
  349. pyxlpr/ppstructure/table/predict_structure.py +0 -136
  350. pyxlpr/ppstructure/table/predict_table.py +0 -221
  351. pyxlpr/ppstructure/table/table_metric/__init__.py +0 -16
  352. pyxlpr/ppstructure/table/table_metric/parallel.py +0 -51
  353. pyxlpr/ppstructure/table/table_metric/table_metric.py +0 -247
  354. pyxlpr/ppstructure/table/tablepyxl/__init__.py +0 -13
  355. pyxlpr/ppstructure/table/tablepyxl/style.py +0 -283
  356. pyxlpr/ppstructure/table/tablepyxl/tablepyxl.py +0 -118
  357. pyxlpr/ppstructure/utility.py +0 -71
  358. pyxlpr/xlai.py +0 -10
@@ -1,67 +1,67 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/06/23 11:26
6
-
7
- import subprocess
8
- import re
9
- import numpy as np
10
-
11
- try:
12
- import shapely
13
- except ModuleNotFoundError:
14
- try:
15
- subprocess.run(['conda', 'install', 'shapely'])
16
- import shapely
17
- except FileNotFoundError:
18
- # 这个库用pip安装是不够的,正常要用conda,有些dll才会自动配置上
19
- subprocess.run(['pip3', 'install', 'shapely'])
20
- import shapely
21
-
22
- from shapely.geometry import Polygon
23
-
24
- from pyxllib.algo.geo import rect2polygon
25
-
26
-
27
- class ShapelyPolygon:
28
- @classmethod
29
- def gen(cls, x):
30
- """ 转成shapely的Polygon对象
31
-
32
- :param x: 支持多种格式,详见代码
33
- :return: Polygon
34
-
35
- >>> print(ShapelyPolygon.gen([[0, 0], [10, 20]])) # list
36
- POLYGON ((0 0, 10 0, 10 20, 0 20, 0 0))
37
- >>> print(ShapelyPolygon.gen({'shape_type': 'polygon', 'points': [[0, 0], [10, 0], [10, 20], [0, 20]]})) # labelme shape
38
- POLYGON ((0 0, 10 0, 10 20, 0 20, 0 0))
39
- >>> print(ShapelyPolygon.gen('107,247,2358,209,2358,297,107,335')) # 字符串格式
40
- POLYGON ((107 247, 2358 209, 2358 297, 107 335, 107 247))
41
- >>> print(ShapelyPolygon.gen('107 247.5, 2358 209.2, 2358 297, 107.5 335')) # 字符串格式
42
- POLYGON ((107 247.5, 2358 209.2, 2358 297, 107.5 335, 107 247.5))
43
- """
44
- if isinstance(x, Polygon):
45
- return x
46
- elif isinstance(x, dict) and 'points' in x:
47
- if x['shape_type'] in ('rectangle', 'polygon'):
48
- # 目前这种情况一般是输入了labelme的shape格式
49
- return ShapelyPolygon.gen(x['points'])
50
- else:
51
- raise ValueError('无法转成多边形的类型')
52
- elif isinstance(x, str):
53
- coords = re.findall(r'[\d\.]+', x)
54
- return ShapelyPolygon.gen(coords)
55
- else:
56
- x = np.array(x).reshape((-1, 2))
57
- if x.shape[0] == 2:
58
- x = rect2polygon(x)
59
- x = np.array(x)
60
- if x.shape[0] >= 3:
61
- return Polygon(x)
62
- else:
63
- raise ValueError
64
-
65
- @classmethod
66
- def to_ndarray(cls, p, dtype=None):
67
- return np.array(p.exterior.coords, dtype=dtype)
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/06/23 11:26
6
+
7
+ import subprocess
8
+ import re
9
+ import numpy as np
10
+
11
+ try:
12
+ import shapely
13
+ except ModuleNotFoundError:
14
+ try:
15
+ subprocess.run(['conda', 'install', 'shapely'])
16
+ import shapely
17
+ except FileNotFoundError:
18
+ # 这个库用pip安装是不够的,正常要用conda,有些dll才会自动配置上
19
+ subprocess.run(['pip3', 'install', 'shapely'])
20
+ import shapely
21
+
22
+ from shapely.geometry import Polygon
23
+
24
+ from pyxllib.algo.geo import rect2polygon
25
+
26
+
27
+ class ShapelyPolygon:
28
+ @classmethod
29
+ def gen(cls, x):
30
+ """ 转成shapely的Polygon对象
31
+
32
+ :param x: 支持多种格式,详见代码
33
+ :return: Polygon
34
+
35
+ >>> print(ShapelyPolygon.gen([[0, 0], [10, 20]])) # list
36
+ POLYGON ((0 0, 10 0, 10 20, 0 20, 0 0))
37
+ >>> print(ShapelyPolygon.gen({'shape_type': 'polygon', 'points': [[0, 0], [10, 0], [10, 20], [0, 20]]})) # labelme shape
38
+ POLYGON ((0 0, 10 0, 10 20, 0 20, 0 0))
39
+ >>> print(ShapelyPolygon.gen('107,247,2358,209,2358,297,107,335')) # 字符串格式
40
+ POLYGON ((107 247, 2358 209, 2358 297, 107 335, 107 247))
41
+ >>> print(ShapelyPolygon.gen('107 247.5, 2358 209.2, 2358 297, 107.5 335')) # 字符串格式
42
+ POLYGON ((107 247.5, 2358 209.2, 2358 297, 107.5 335, 107 247.5))
43
+ """
44
+ if isinstance(x, Polygon):
45
+ return x
46
+ elif isinstance(x, dict) and 'points' in x:
47
+ if x['shape_type'] in ('rectangle', 'polygon'):
48
+ # 目前这种情况一般是输入了labelme的shape格式
49
+ return ShapelyPolygon.gen(x['points'])
50
+ else:
51
+ raise ValueError('无法转成多边形的类型')
52
+ elif isinstance(x, str):
53
+ coords = re.findall(r'[\d\.]+', x)
54
+ return ShapelyPolygon.gen(coords)
55
+ else:
56
+ x = np.array(x).reshape((-1, 2))
57
+ if x.shape[0] == 2:
58
+ x = rect2polygon(x)
59
+ x = np.array(x)
60
+ if x.shape[0] >= 3:
61
+ return Polygon(x)
62
+ else:
63
+ raise ValueError
64
+
65
+ @classmethod
66
+ def to_ndarray(cls, p, dtype=None):
67
+ return np.array(p.exterior.coords, dtype=dtype)
@@ -1,240 +1,241 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/06/06 11:16
6
-
7
- import copy
8
- import itertools
9
-
10
- import numpy as np
11
- import pandas as pd
12
-
13
- from pyxllib.prog.pupil import DictTool
14
- from pyxllib.prog.deprecatedlib import deprecated
15
-
16
-
17
- @deprecated(reason='这个实现方式不佳,请参考 make_index_function')
18
- def sort_by_given_list(a, b):
19
- r""" 本函数一般用在数据透视表中,分组中元素名为中文,没有按指定规律排序的情况
20
-
21
- :param a: 需要排序的对象
22
- :param b: 参照的排序数组
23
- :return: 排序后的a
24
-
25
- >>> sort_by_given_list(['初中', '小学', '高中'], ['少儿', '小学', '初中', '高中'])
26
- ['小学', '初中', '高中']
27
-
28
- # 不在枚举项目里的,会统一列在最后面
29
- >>> sort_by_given_list(['初中', '小学', '高中', '幼儿'], ['少儿', '小学', '初中', '高中'])
30
- ['小学', '初中', '高中', '幼儿']
31
- """
32
- # 1 从b数组构造一个d字典,d[k]=i,值为k的元素在第i位
33
- d = dict()
34
- for i, bb in enumerate(b): d[bb] = i
35
- # 2 a数组分两部分,可以通过d排序的a1,和不能通过d排序的a2
36
- a1, a2 = [], []
37
- for aa in a:
38
- if aa in d:
39
- a1.append(aa)
40
- else:
41
- a2.append(aa)
42
- # 3 用不同的规则排序a1、a2后合并
43
- a1 = sorted(a1, key=lambda x: d[x])
44
- a2 = sorted(a2)
45
- return a1 + a2
46
-
47
-
48
- def product(*iterables, order=None, repeat=1):
49
- """ itertools 的product扩展orders参数的更高级的product迭代器
50
-
51
- :param order: 假设iterables有n=3个迭代器,则默认 orders=[1, 2, 3] (起始编号1)
52
- 即标准的product,是按顺序对每个迭代器进行重置、遍历的
53
- 但是我扩展的这个接口,允许调整每个维度的更新顺序
54
- 例如设置为 [-2, 1, 3],表示先对第2维降序,然后按第1、3维的方式排序获得各个坐标点
55
- 注:可以只输入[-2],默认会自动补充维[1, 3]
56
-
57
- 不从0开始编号,是因为0没法记录正负排序情况
58
-
59
- for x in product('ab', 'cd', 'ef', order=[3, -2, 1]):
60
- print(x)
61
-
62
- ['a', 'd', 'e']
63
- ['b', 'd', 'e']
64
- ['a', 'c', 'e']
65
- ['b', 'c', 'e']
66
- ['a', 'd', 'f']
67
- ['b', 'd', 'f']
68
- ['a', 'c', 'f']
69
- ['b', 'c', 'f']
70
-
71
- TODO 我在想numpy这么牛逼,会不会有等价的功能接口可以实现,我不用重复造轮子?
72
- """
73
- # 一、标准调用方式
74
- if order is None:
75
- for x in itertools.product(*iterables, repeat=repeat):
76
- yield x
77
- return
78
-
79
- # 二、输入orders参数的调用方式
80
- # 1 补全orders参数长度
81
- n = len(iterables)
82
- for i in range(1, n + 1):
83
- if not (i in order or -i in order):
84
- order.append(i)
85
- if len(order) != n: return ValueError(f'orders参数值有问题 {order}')
86
-
87
- # 2 生成新的迭代器组
88
- new_iterables = [(iterables[i - 1] if i > 0 else reversed(iterables[-i - 1])) for i in order]
89
- idx = np.argsort([abs(i) - 1 for i in order])
90
- for y in itertools.product(*new_iterables, repeat=repeat):
91
- yield [y[i] for i in idx]
92
-
93
-
94
- class MatchPairs:
95
- """ 匹配类,对X,Y两组数据中的x,y等对象按照cmp_func的规则进行相似度配对
96
-
97
- MatchBase(ys, cmp_func).matches(xs, least_score)
98
- """
99
-
100
- def __init__(self, ys, cmp_func):
101
- self.ys = list(ys)
102
- self.cmp_func = cmp_func
103
-
104
- def __getitem__(self, idx):
105
- return self.ys[idx]
106
-
107
- # def __del__(self, idx):
108
- # del self.ys[idx]
109
-
110
- def __len__(self):
111
- return len(self.ys)
112
-
113
- def match(self, x, k=1):
114
- """ 匹配一个对象
115
-
116
- :param x: 待匹配的一个对象
117
- :param k: 返回次优的几个结果
118
- :return:
119
- 当 k = 1 时,返回 (idx, score)
120
- 当 k > 1 时,返回 [(idx1, score1), (idx2, score2), ...]
121
- """
122
- scores = [self.cmp_func(x, y) for y in self.ys]
123
- if k == 1:
124
- score = max(scores)
125
- idx = scores.index(score)
126
- return idx, score
127
- else:
128
- # 按权重从大到小排序
129
- idxs = np.argsort(scores)
130
- idxs = idxs[::-1][:k]
131
- return [(idx, scores[idx]) for idx in idxs]
132
-
133
- def matches(self, xs):
134
- """ xs中每个元素都找到一个最佳匹配对象
135
-
136
- 注意:这个功能是支持ys中的元素被重复匹配的,而且哪怕相似度很低,也会返回一个最佳匹配结果
137
- 如果想限定相似度,或者不支持重复匹配,请到隔壁使用 matchpairs
138
-
139
- :param xs: 要匹配的一组对象
140
- :return: 为每个x找到一个最佳的匹配y,存储其下标和对应的分值
141
- [(idx0, score0), (idx1, score1), ...] 长度 = len(xs)
142
-
143
- >>> m = MatchPairs([1, 5, 8, 9, 2], lambda x,y: 1-abs(x-y)/max(x,y))
144
- >>> m.matches([4, 6]) # 这里第1个值是下标,所以分别是对应5、8
145
- [(1, 0.8), (1, 0.8333333333333334)]
146
-
147
- # 要匹配的对象多于实际ys,则只会返回前len(ys)个结果
148
- # 这种情况建议用matchpairs功能实现,或者实在想用就对调xs、ys
149
- >>> m.matches([4, 6, 1, 2, 9, 4, 5])
150
- [(1, 0.8), (1, 0.8333333333333334), (0, 1.0), (4, 1.0), (3, 1.0), (1, 0.8), (1, 1.0)]
151
- """
152
- return [self.match(x) for x in xs]
153
-
154
-
155
- def get_ndim(coords):
156
- # 注意 np.array(coords[:1]),只需要取第一个元素就可以判断出ndim
157
- coords = coords if isinstance(coords, np.ndarray) else np.array(coords[:1])
158
- return coords.ndim
159
-
160
-
161
- class DictCmper:
162
- """ 字典结构比较工具
163
-
164
- 集合是字典的特殊情况,也支持集合间的对比
165
- """
166
-
167
- def __init__(self, dicts):
168
- """
169
- :param Dict[str, Dict|set] dicts: Dicts[dictname, dict_]
170
- 如果是set,会升级为dict,value默认为1
171
- """
172
- self.dicts = {}
173
- for k, v in dicts.items():
174
- if isinstance(v, set):
175
- self.dicts[k] = {k: 1 for k in v}
176
- else:
177
- self.dicts[k] = v
178
-
179
- def details(self):
180
- """ 返回详细的分析表
181
-
182
- 按行罗列所有键,按列罗列所有字典,中间显示各字典键值
183
- 可以把结果保存到excel,然后详细筛选分析
184
-
185
- >>> dc = DictCmper({'d1': {'a': 1, 'b': 2}, 'd2': {'b': 3, 'e': 5}, 'd3': {'d': 4}})
186
- >>> dc.details()
187
- d1 d2 d3
188
- a 1.0 NaN NaN
189
- b 2.0 3.0 NaN
190
- e NaN 5.0 NaN
191
- d NaN NaN 4.0
192
- """
193
- # 1 获得所有键
194
- # 集合无法保存元素顺序,所以用合并字典来代替
195
- # 还有个三方库orderedset,不想安装。就这样简便解决就好。
196
- keys = DictTool.or_(*self.dicts.values()).keys()
197
-
198
- # 2 取出所有字典值
199
- ls = []
200
- for k in keys:
201
- ls.append([(d[k] if k in d else np.nan) for d in self.dicts.values()])
202
-
203
- # 3 转为df表格
204
- df = pd.DataFrame.from_records(ls, columns=self.dicts.keys())
205
- df.index = keys
206
- return df
207
-
208
- def pair_summary(self, func=lambda x, y: len(x.keys() & y.keys())):
209
- r""" 两两对比表
210
-
211
- :param func: 默认是计算两个字典共有的键数量
212
- :return: df
213
- df对角线存储的是每个集合自身大小,df第i行第j列是第i个集合减去第j个集合的剩余元素数
214
-
215
- >>> s1 = {1, 2, 3, 4, 5, 6, 7, 8, 9}
216
- >>> s2 = {1, 3, 5, 7, 8}
217
- >>> s3 = {2, 3, 5, 8}
218
- >>> dc = DictCmper({'s1': s1, 's2': s2, 's3': s3})
219
- >>> dc.pair_summary()
220
- s1 s2 s3
221
- s1 9 5 4
222
- s2 5 5 3
223
- s3 4 3 4
224
- >>> dc.pair_summary(lambda x, y: len(x.keys() - y.keys()))
225
- s1 s2 s3
226
- s1 0 4 5
227
- s2 0 0 2
228
- s3 0 1 0
229
- """
230
- dictnames = list(self.dicts.keys())
231
- n = len(dictnames)
232
- rows = []
233
- for i, name1 in enumerate(dictnames):
234
- row = [0] * n
235
- for j, name2 in enumerate(dictnames):
236
- row[j] = func(self.dicts[name1], self.dicts[name2])
237
- rows.append(row)
238
- df = pd.DataFrame.from_records(rows, columns=dictnames)
239
- df.index = dictnames
240
- return df
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/06/06 11:16
6
+
7
+ import copy
8
+ import itertools
9
+
10
+ import numpy as np
11
+ import pandas as pd
12
+
13
+ from pyxllib.prog.pupil import DictTool
14
+ # from pyxllib.prog.deprecatedlib import deprecated
15
+ from deprecated import deprecated
16
+
17
+
18
+ @deprecated(reason='这个实现方式不佳,请参考 make_index_function')
19
+ def sort_by_given_list(a, b):
20
+ r""" 本函数一般用在数据透视表中,分组中元素名为中文,没有按指定规律排序的情况
21
+
22
+ :param a: 需要排序的对象
23
+ :param b: 参照的排序数组
24
+ :return: 排序后的a
25
+
26
+ >>> sort_by_given_list(['初中', '小学', '高中'], ['少儿', '小学', '初中', '高中'])
27
+ ['小学', '初中', '高中']
28
+
29
+ # 不在枚举项目里的,会统一列在最后面
30
+ >>> sort_by_given_list(['初中', '小学', '高中', '幼儿'], ['少儿', '小学', '初中', '高中'])
31
+ ['小学', '初中', '高中', '幼儿']
32
+ """
33
+ # 1 从b数组构造一个d字典,d[k]=i,值为k的元素在第i位
34
+ d = dict()
35
+ for i, bb in enumerate(b): d[bb] = i
36
+ # 2 a数组分两部分,可以通过d排序的a1,和不能通过d排序的a2
37
+ a1, a2 = [], []
38
+ for aa in a:
39
+ if aa in d:
40
+ a1.append(aa)
41
+ else:
42
+ a2.append(aa)
43
+ # 3 用不同的规则排序a1、a2后合并
44
+ a1 = sorted(a1, key=lambda x: d[x])
45
+ a2 = sorted(a2)
46
+ return a1 + a2
47
+
48
+
49
+ def product(*iterables, order=None, repeat=1):
50
+ """ 对 itertools 的product扩展orders参数的更高级的product迭代器
51
+
52
+ :param order: 假设iterables有n=3个迭代器,则默认 orders=[1, 2, 3] (起始编号1)
53
+ 即标准的product,是按顺序对每个迭代器进行重置、遍历的
54
+ 但是我扩展的这个接口,允许调整每个维度的更新顺序
55
+ 例如设置为 [-2, 1, 3],表示先对第2维降序,然后按第1、3维的方式排序获得各个坐标点
56
+ 注:可以只输入[-2],默认会自动补充维[1, 3]
57
+
58
+ 不从0开始编号,是因为0没法记录正负排序情况
59
+
60
+ for x in product('ab', 'cd', 'ef', order=[3, -2, 1]):
61
+ print(x)
62
+
63
+ ['a', 'd', 'e']
64
+ ['b', 'd', 'e']
65
+ ['a', 'c', 'e']
66
+ ['b', 'c', 'e']
67
+ ['a', 'd', 'f']
68
+ ['b', 'd', 'f']
69
+ ['a', 'c', 'f']
70
+ ['b', 'c', 'f']
71
+
72
+ TODO 我在想numpy这么牛逼,会不会有等价的功能接口可以实现,我不用重复造轮子?
73
+ """
74
+ # 一、标准调用方式
75
+ if order is None:
76
+ for x in itertools.product(*iterables, repeat=repeat):
77
+ yield x
78
+ return
79
+
80
+ # 二、输入orders参数的调用方式
81
+ # 1 补全orders参数长度
82
+ n = len(iterables)
83
+ for i in range(1, n + 1):
84
+ if not (i in order or -i in order):
85
+ order.append(i)
86
+ if len(order) != n: return ValueError(f'orders参数值有问题 {order}')
87
+
88
+ # 2 生成新的迭代器组
89
+ new_iterables = [(iterables[i - 1] if i > 0 else reversed(iterables[-i - 1])) for i in order]
90
+ idx = np.argsort([abs(i) - 1 for i in order])
91
+ for y in itertools.product(*new_iterables, repeat=repeat):
92
+ yield [y[i] for i in idx]
93
+
94
+
95
+ class MatchPairs:
96
+ """ 匹配类,对X,Y两组数据中的x,y等对象按照cmp_func的规则进行相似度配对
97
+
98
+ MatchBase(ys, cmp_func).matches(xs, least_score)
99
+ """
100
+
101
+ def __init__(self, ys, cmp_func):
102
+ self.ys = list(ys)
103
+ self.cmp_func = cmp_func
104
+
105
+ def __getitem__(self, idx):
106
+ return self.ys[idx]
107
+
108
+ # def __del__(self, idx):
109
+ # del self.ys[idx]
110
+
111
+ def __len__(self):
112
+ return len(self.ys)
113
+
114
+ def match(self, x, k=1):
115
+ """ 匹配一个对象
116
+
117
+ :param x: 待匹配的一个对象
118
+ :param k: 返回次优的几个结果
119
+ :return:
120
+ 当 k = 1 时,返回 (idx, score)
121
+ 当 k > 1 时,返回 [(idx1, score1), (idx2, score2), ...]
122
+ """
123
+ scores = [self.cmp_func(x, y) for y in self.ys]
124
+ if k == 1:
125
+ score = max(scores)
126
+ idx = scores.index(score)
127
+ return idx, score
128
+ else:
129
+ # 按权重从大到小排序
130
+ idxs = np.argsort(scores)
131
+ idxs = idxs[::-1][:k]
132
+ return [(idx, scores[idx]) for idx in idxs]
133
+
134
+ def matches(self, xs):
135
+ """ 对xs中每个元素都找到一个最佳匹配对象
136
+
137
+ 注意:这个功能是支持ys中的元素被重复匹配的,而且哪怕相似度很低,也会返回一个最佳匹配结果
138
+ 如果想限定相似度,或者不支持重复匹配,请到隔壁使用 matchpairs
139
+
140
+ :param xs: 要匹配的一组对象
141
+ :return: 为每个x找到一个最佳的匹配y,存储其下标和对应的分值
142
+ [(idx0, score0), (idx1, score1), ...] 长度 = len(xs)
143
+
144
+ >>> m = MatchPairs([1, 5, 8, 9, 2], lambda x,y: 1-abs(x-y)/max(x,y))
145
+ >>> m.matches([4, 6]) # 这里第1个值是下标,所以分别是对应5、8
146
+ [(1, 0.8), (1, 0.8333333333333334)]
147
+
148
+ # 要匹配的对象多于实际ys,则只会返回前len(ys)个结果
149
+ # 这种情况建议用matchpairs功能实现,或者实在想用就对调xs、ys
150
+ >>> m.matches([4, 6, 1, 2, 9, 4, 5])
151
+ [(1, 0.8), (1, 0.8333333333333334), (0, 1.0), (4, 1.0), (3, 1.0), (1, 0.8), (1, 1.0)]
152
+ """
153
+ return [self.match(x) for x in xs]
154
+
155
+
156
+ def get_ndim(coords):
157
+ # 注意 np.array(coords[:1]),只需要取第一个元素就可以判断出ndim
158
+ coords = coords if isinstance(coords, np.ndarray) else np.array(coords[:1])
159
+ return coords.ndim
160
+
161
+
162
+ class DictCmper:
163
+ """ 字典结构比较工具
164
+
165
+ 集合是字典的特殊情况,也支持集合间的对比
166
+ """
167
+
168
+ def __init__(self, dicts):
169
+ """
170
+ :param Dict[str, Dict|set] dicts: Dicts[dictname, dict_]
171
+ 如果是set,会升级为dict,value默认为1
172
+ """
173
+ self.dicts = {}
174
+ for k, v in dicts.items():
175
+ if isinstance(v, set):
176
+ self.dicts[k] = {k: 1 for k in v}
177
+ else:
178
+ self.dicts[k] = v
179
+
180
+ def details(self):
181
+ """ 返回详细的分析表
182
+
183
+ 按行罗列所有键,按列罗列所有字典,中间显示各字典键值
184
+ 可以把结果保存到excel,然后详细筛选分析
185
+
186
+ >>> dc = DictCmper({'d1': {'a': 1, 'b': 2}, 'd2': {'b': 3, 'e': 5}, 'd3': {'d': 4}})
187
+ >>> dc.details()
188
+ d1 d2 d3
189
+ a 1.0 NaN NaN
190
+ b 2.0 3.0 NaN
191
+ e NaN 5.0 NaN
192
+ d NaN NaN 4.0
193
+ """
194
+ # 1 获得所有键
195
+ # 集合无法保存元素顺序,所以用合并字典来代替
196
+ # 还有个三方库orderedset,不想安装。就这样简便解决就好。
197
+ keys = DictTool.or_(*self.dicts.values()).keys()
198
+
199
+ # 2 取出所有字典值
200
+ ls = []
201
+ for k in keys:
202
+ ls.append([(d[k] if k in d else np.nan) for d in self.dicts.values()])
203
+
204
+ # 3 转为df表格
205
+ df = pd.DataFrame.from_records(ls, columns=self.dicts.keys())
206
+ df.index = keys
207
+ return df
208
+
209
+ def pair_summary(self, func=lambda x, y: len(x.keys() & y.keys())):
210
+ r""" 两两对比表
211
+
212
+ :param func: 默认是计算两个字典共有的键数量
213
+ :return: df
214
+ df对角线存储的是每个集合自身大小,df第i行第j列是第i个集合减去第j个集合的剩余元素数
215
+
216
+ >>> s1 = {1, 2, 3, 4, 5, 6, 7, 8, 9}
217
+ >>> s2 = {1, 3, 5, 7, 8}
218
+ >>> s3 = {2, 3, 5, 8}
219
+ >>> dc = DictCmper({'s1': s1, 's2': s2, 's3': s3})
220
+ >>> dc.pair_summary()
221
+ s1 s2 s3
222
+ s1 9 5 4
223
+ s2 5 5 3
224
+ s3 4 3 4
225
+ >>> dc.pair_summary(lambda x, y: len(x.keys() - y.keys()))
226
+ s1 s2 s3
227
+ s1 0 4 5
228
+ s2 0 0 2
229
+ s3 0 1 0
230
+ """
231
+ dictnames = list(self.dicts.keys())
232
+ n = len(dictnames)
233
+ rows = []
234
+ for i, name1 in enumerate(dictnames):
235
+ row = [0] * n
236
+ for j, name2 in enumerate(dictnames):
237
+ row[j] = func(self.dicts[name1], self.dicts[name2])
238
+ rows.append(row)
239
+ df = pd.DataFrame.from_records(rows, columns=dictnames)
240
+ df.index = dictnames
241
+ return df